Break down features and requirements into actionable, implementable tasks with clear scope and acceptance criteria. Use when planning implementation, organizing complex work, or creating task lists. Trigger phrases: "break down tasks", "create work plan", "organize implementation", "plan development". This skill works best when preceded by `requirements-elicitation` skill use.
npx skills add https://github.com/bitwarden/ai-plugins --skill work-breakdown
Organize work into logical phases:
Phase 1: Architecture & Design
Phase 2: Implementation
Phase 3: Testing
Phase 4: Documentation & Deployment
Each task should be:
Each task should follow this structure:
**Task X.Y**: [Concise task title]
- **Description**: [What needs to be done]
- **Team/Role**: [Backend | Frontend | Security | QA | DevOps]
- **Estimated Duration**: [2-8 hours]
- **Dependencies**: [Task IDs that must complete first, or "None"]
- **Deliverables**: [Specific outputs or changes]
- **Acceptance Criteria**: [How to verify completion]
See examples/oauth-authentication.md for a complete worked example.
Organize work breakdown in structured phases:
# Work Breakdown: [Feature Name]
## Summary
- **Total Estimated Duration**: X-Y hours
- **Number of Tasks**: N tasks across M phases
- **Teams Involved**: [List of teams]
- **Critical Path**: [Key dependencies or bottlenecks]
---
## Phase 1: [Phase Name]
**Goal**: [What this phase accomplishes]
**Task 1.1**: [Task title]
- **Description**: [What needs to be done]
- **Team/Role**: [Who does this]
- **Estimated Duration**: [Hours]
- **Dependencies**: [Prerequisites or "None"]
- **Deliverables**: [Concrete outputs]
- **Acceptance Criteria**: [How to verify]
**Task 1.2**: [Next task]
...
---
## Phase 2: [Phase Name]
...
---
## Verification
After all phases complete, verify:
- [ ] All functional requirements implemented
- [ ] All non-functional requirements met
- [ ] All security requirements addressed
- [ ] All tests passing (unit, integration, E2E)
- [ ] Documentation complete and accurate
- [ ] Deployment procedures tested
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.
Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Take bitwarden/work-breakdown from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.